Notes
Notes - notes.io |
import random
# x_data=np.array([[1951,26.1],[1952,24.5],[1953,24.8],[1954,24.5],[1955,24.1],[1956,24.3],[1957,26.4],[1958,24.9],[1959,23.7]]).reshape(9,2)
# t_data=np.array([0,1,1,1,1,1,0,1,1]).reshape(9,1)
# W=np.random.rand(2,1)
# b=np.random.rand(1)
# def sigmoid(x):
# return 1/(1+np.exp(-x))
# def loss_func(x,t):
# delta=1e-7
# z=np.dot(x, W)+b
# y=sigmoid(z)
# return -np.sum((t*np.log(y+delta)+(1-t)*np.log(1-y+delta)))
# def error_val(x,t):
# delta=1e-7
# z=np.dot(x, W)+b
# y=sigmoid(z)
# return -np.sum((t*np.log(y+delta)+(1-t)*np.log(1-y+delta)))
# def predict(x):
# z=np.dot(x,W)+b
# y=sigmoid(z)
# if y>24.9:
# result=1
# else:
# result=0
# return y,result
# def numerical_derivative(f,x):
# delta_x=1e-4
# grad=np.zeros_like(x)
# it=np.nditer(x, flags=['multi_index'],op_flags=['readwrite'])
# while not it.finished:
# idx=it.multi_index
# tmp_val=x[idx]
# x[idx]=float(tmp_val)+delta_x
# fx1=f(x)
# x[idx]=tmp_val-delta_x
# fx2=f(x)
# grad[idx]=(fx1-fx2)/(2*delta_x)
# x[idx]=tmp_val
# it.iternext()
# return grad
# learning_rate=1e-4
# f=lambda x: loss_func(x_data, t_data)
# for step in range(10001):
# W-=learning_rate*numerical_derivative(f,W)
# b-=learning_rate*numerical_derivative(f,b)
# if(step%400==0):
# print("step=",step,"error value=",error_val(x_data,t_data),"W=",W,"b=",b)
# test_data=np.array([1970,25.1])
# print("Tempereture iin dundaj:",predict(test_data))
# test_data=np.array([1969,26.8])
# print("Tempereture iin dundaj:",predict(test_data))
# import numpy as np
# import random
# x_data=np.array([50,53,54,55,56,59,62,65,67,71]).reshape(10,1)
# t_data=np.array([122,118,128,121,125,136,144,142,149,161]).reshape(10,1)
# W=np.random.rand(1,1)
# b=np.random.rand(1)
# print("W=",W,"W.shape=",W.shape,",b=",b,",b.shape=",b.shape)
# def loss_func(x,t):
# y=np.dot(x,W)+b
# return (np.sum((t-y)**2))/(len(x))
# def numerical_derivative(f,x):
# delta_x=1e-4
# grad=np.zeros_like(x)
# it=np.nditer(x, flags=['multi_index'],op_flags=['readwrite'])
# while not it.finished:
# idx=it.multi_index
# tmp_val=x[idx]
# x[idx]=float(tmp_val)+delta_x
# fx1=f(x)
# x[idx]=tmp_val-delta_x
# fx2=f(x)
# grad[idx]=(fx1-fx2)/(2*delta_x)
# x[idx]=tmp_val
# it.iternext()
# return grad
# def error_val(x,t):
# y=np.dot(x,W)+b
# return (np.sum((t-y)**2))/(len(x))
# def predict(x):
# y=np.dot(x, W)+b
# return y
# learning_rate=1e-4
# f=lambda x : loss_func(x_data, t_data)
# print("initial error value=",error_val(x_data,t_data),"Initial W=",W,",b=",b)
# for step in range(8001):
# W-=learning_rate*numerical_derivative(f,W)
# b-=learning_rate*numerical_derivative(f,b)
# if(step % 400==0):
# print("step=",step,",error value=",error_val(x_data,t_data),",W=",W,",b=",b)
# temperature=np.array([97])
# print("buteegdehuunii too:",predict(temperature))
# temperature=np.array([100])
# print("buteegdehuunii too:",predict(temperature))
# def sigmoid(x):
# return 1/(1+np.exp(-x))
# def numerical_derivative(f,x):
# delta_x=1e-4
# grad=np.zeros_like(x)
# it=np.nditer(x, flags=['multi_index'],op_flags=['readwrite'])
# while not it.finished:
# idx=it.multi_index
# tmp_val=x[idx]
# x[idx]=float(tmp_val)+delta_x
# fx1=f(x)
# x[idx]=tmp_val-delta_x
# fx2=f(x)
# grad[idx]=(fx1-fx2)/(2*delta_x)
# x[idx]=tmp_val
# it.iternext()
# return grad
# class LogicGate:
# def __init__(self, gate_name, xdata, tdata):
# self.name=gate_name
# self.__xdata=xdata.reshape(4,2)
# self.__tdata=tdata.reshape(4,1)
# self.__W=np.random.rand(2,1)
# self.__b=np.random.rand(1)
# self.__learning_rate=1e-2
# def __loss_func(self):
# delta=1e-7
# z=np.dot(self.__xdata, self.__W)+self.__b
# y=sigmoid(z)
# return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
# def error_val(self):
# delta=1e-7
# z=np.dot(self.__xdata, self.__W)+self.__b
# y=sigmoid(z)
# return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
# def train(self):
# f=lambda x:self.__loss_func()
# for step in range(8001):
# self.__W-=self.__learning_rate*numerical_derivative(f,self.__W)
# self.__b-=self.__learning_rate*numerical_derivative(f,self.__b)
# if(step % 400==0):
# print("step=",step,",error value=",self.error_val())
# def predict(self, input_data):
# z=np.dot(input_data, self.__W)+self.__b
# y=sigmoid(z)
# if y>0.5:
# result=1
# else:
# result=0
# return y, result
# xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
# tdata=np.array([0,0,0,1])
# AND_obj= LogicGate("AND_GATE",xdata,tdata)
# AND_obj.train()
# print(AND_obj.name,"n")
# test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
# for input_data in test_data:
# (sigmoid.val, logical_val)=AND_obj.predict(input_data)
# print(input_data,"=",logical_val,"n")
# def sigmoid(x):
# return 1/(1+np.exp(-x))
# def numerical_derivative(f,x):
# delta_x=1e-4
# grad=np.zeros_like(x)
# it=np.nditer(x, flags=['multi_index'],op_flags=['readwrite'])
# while not it.finished:
# idx=it.multi_index
# tmp_val=x[idx]
# x[idx]=float(tmp_val)+delta_x
# fx1=f(x)
# x[idx]=tmp_val-delta_x
# fx2=f(x)
# grad[idx]=(fx1-fx2)/(2*delta_x)
# x[idx]=tmp_val
# it.iternext()
# return grad
# class LogicGate:
# def __init__(self, gate_name, xdata, tdata):
# self.name=gate_name
# self.__xdata=xdata.reshape(4,2)
# self.__tdata=tdata.reshape(4,1)
# self.__W=np.random.rand(2,1)
# self.__b=np.random.rand(1)
# self.__learning_rate=1e-2
# def __loss_func(self):
# delta=1e-7
# z=np.dot(self.__xdata, self.__W)+self.__b
# y=sigmoid(z)
# return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
# def error_val(self):
# delta=1e-7
# z=np.dot(self.__xdata, self.__W)+self.__b
# y=sigmoid(z)
# return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
# def train(self):
# f=lambda x:self.__loss_func()
# for step in range(8001):
# self.__W-=self.__learning_rate*numerical_derivative(f,self.__W)
# self.__b-=self.__learning_rate*numerical_derivative(f,self.__b)
# if(step % 400==0):
# print("step=",step,",error value=",self.error_val())
# def predict(self, input_data):
# z=np.dot(input_data, self.__W)+self.__b
# y=sigmoid(z)
# if y>0.5:
# result=1
# else:
# result=0
# return y, result
# #And eheljin
# xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
# tdata=np.array([0,0,0,1])
# AND_obj= LogicGate("AND_GATE",xdata,tdata)
# AND_obj.train()
# print(AND_obj.name,"n")
# test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
# for input_data in test_data:
# (sigmoid.val, logical_val)=AND_obj.predict(input_data)
# print(input_data,"=",logical_val,"n")
# # or eheljin
# xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
# tdata=np.array([0,1,1,1])
# OR_obj= LogicGate("OR_GATE",xdata,tdata)
# OR_obj.train()
# print(OR_obj.name,"n")
# test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
# for input_data in test_data:
# (sigmoid.val, logical_val)=OR_obj.predict(input_data)
# print(input_data,"=",logical_val,"n")
# #nand eheljin
# xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
# tdata=np.array([1,1,1,0])
# NAND_obj= LogicGate("NAND_GATE",xdata,tdata)
# NAND_obj.train()
# print(NAND_obj.name,"n")
# test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
# for input_data in test_data:
# (sigmoid.val, logical_val)=NAND_obj.predict(input_data)
# print(input_data,"=",logical_val,"n")
# #XOr eheljin
# input_data = np.array([ [0,0], [0,1], [1,0], [1,1] ])
# s1 = []
# s2 = []
# new_input_data = []
# final_output = []
# for index in range (len(input_data)):
# s1 = NAND_obj.predict(input_data[index])
# s2 = OR_obj.predict(input_data[index])
# new_input_data.append(s1[-1])
# new_input_data.append(s2[-1])
# (sigmoid.val, logical_val) = AND_obj.predict(np.array(new_input_data))
# final_output.append(logical_val)
# new_input_data = []
# for index in range(len(input_data)):
# print(input_data[index], " = ", final_output[index], end='')
# print("n")
def sigmoid(x):
return 1/(1+np.exp(-x))
def numerical_derivative(f,x):
delta_x=1e-4
grad=np.zeros_like(x)
it=np.nditer(x, flags=['multi_index'],op_flags=['readwrite'])
while not it.finished:
idx=it.multi_index
tmp_val=x[idx]
x[idx]=float(tmp_val)+delta_x
fx1=f(x)
x[idx]=tmp_val-delta_x
fx2=f(x)
grad[idx]=(fx1-fx2)/(2*delta_x)
x[idx]=tmp_val
it.iternext()
return grad
class LogicGate:
def __init__(self, gate_name, xdata, tdata):
self.name=gate_name
self.__xdata=xdata.reshape(4,2)
self.__tdata=tdata.reshape(4,1)
self.__W2=np.random.rand(2,6)
self.__b2=np.random.rand(6)
self.__W3=np.random.rand(6,1)
self.__b3=np.random.rand(1)
self.__learning_rate=1e-2
def feed_forward(self):
delta=1e-7
z2=np.dot(self.__xdata, self.__W2)+self.__b2
a2=sigmoid(z2)
z3=np.dot(a2,self.__W3)+self.__b3
y=a3=sigmoid(z3)
return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
def loss_val(self):
delta=1e-7
z2=np.dot(self.__xdata, self.__W2)+self.__b2
a2=sigmoid(z2)
z3=np.dot(a2,self.__W3)+self.__b3
y=a3=sigmoid(z3)
return -np.sum((self.__tdata*np.log(y+delta)+(1-self.__tdata)*np.log(1-y+delta)))
def train(self):
f=lambda x:self.feed_forward()
for step in range(10001):
self.__W2-=self.__learning_rate*numerical_derivative(f,self.__W2)
self.__b2-=self.__learning_rate*numerical_derivative(f,self.__b2)
self.__W3-=self.__learning_rate*numerical_derivative(f,self.__W3)
self.__b3-=self.__learning_rate*numerical_derivative(f,self.__b3)
if(step % 400==0):
print("step=",step," loss value=",self.loss_val())
def predict(self, input_data):
z2=np.dot(input_data,self.__W2)+self.__b2
a2=sigmoid(z2)
z3=np.dot(a2, self.__W3)+self.__b3
y=a3=sigmoid(z3)
if y>0.5:
result=1
else:
result=0
return y, result
#AND
xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
tdata=np.array([0,0,0,1])
AND_obj= LogicGate("AND_GATE",xdata,tdata)
AND_obj.train()
print(AND_obj.name,"n")
test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
for data in test_data:
print(AND_obj.predict(data))
#OR
xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
tdata=np.array([0,1,1,1])
OR_obj= LogicGate("OR_GATE",xdata,tdata)
OR_obj.train()
print(OR_obj.name,"n")
test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
for data in test_data:
print(OR_obj.predict(data))
#NAND
xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
tdata=np.array([1,1,1,0])
NAND_obj= LogicGate("NAND_GATE",xdata,tdata)
NAND_obj.train()
print(NAND_obj.name,"n")
test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
for data in test_data:
print(NAND_obj.predict(data))
#XOR
xdata=np.array([[0,0],[0,1],[1,0],[1,1]])
tdata=np.array([0,1,1,0])
XOR_obj= LogicGate("XOR_GATE",xdata,tdata)
XOR_obj.train()
print(XOR_obj.name,"n")
test_data=np.array([[0,0],[0,1],[1,0],[1,1]])
for data in test_data:
print(XOR_obj.predict(data))
|
|
Notes.io is a web-based application for taking notes. You can take your notes and share with others people. If you like taking long notes, notes.io is designed for you. To date, over 8,000,000,000 notes created and continuing...
With notes.io;
- * You can take a note from anywhere and any device with internet connection.
- * You can share the notes in social platforms (YouTube, Facebook, Twitter, instagram etc.).
- * You can quickly share your contents without website, blog and e-mail.
- * You don't need to create any Account to share a note. As you wish you can use quick, easy and best shortened notes with sms, websites, e-mail, or messaging services (WhatsApp, iMessage, Telegram, Signal).
- * Notes.io has fabulous infrastructure design for a short link and allows you to share the note as an easy and understandable link.
Fast: Notes.io is built for speed and performance. You can take a notes quickly and browse your archive.
Easy: Notes.io doesn’t require installation. Just write and share note!
Short: Notes.io’s url just 8 character. You’ll get shorten link of your note when you want to share. (Ex: notes.io/q )
Free: Notes.io works for 12 years and has been free since the day it was started.
You immediately create your first note and start sharing with the ones you wish. If you want to contact us, you can use the following communication channels;
Email: [email protected]
Twitter: http://twitter.com/notesio
Instagram: http://instagram.com/notes.io
Facebook: http://facebook.com/notesio
Regards;
Notes.io Team
